Math 143 C/E, Spring 2001
IPS Reading Questions
Chapter 5, Section 1 (pp. 372-385)
- What is a population distribution of a variable? How
does it differ
from a sampling distribution? Does the distinction between
a population that does exist (say, women between the ages of
18 and 24) and one that doesn't (all rods that would be produced
by a certain manufacturing process if it continued forever)
bother you?
- Compare Examples 5.2(b) and 5.3. The authors say emphatically
that 5.2(b) is not a binomial setting, while 5.3 is not
quite a binomial setting. Don't these scenarios seem
similar? How do they justify letting it go in 5.3, but not
in 5.2(b)? Do they indicate how you would decide whether a
certain binomial setting is close enough to binomial to let
it go?
- We have seen at least one probability histogram for a
binomial distribution Free-Throw Freddy and his 5
shots. The resulting histogram in that case was for
B(5, 0.7), but recall that to get the appropriate
probabilities from Table C, we had to look at B(5, 0.3).
Select other values for n and p (ones that you
can use Table C to get) and plot
the resulting probability distribution B(n,p)
until you feel confident you know what you're doing.
Use
this applet to compare your histograms to the
correct answers.
- Return to the
binomial applet to experiment with it
some more. Pick a value of p and stick with it
while you vary the value of n. What do you
notice about the center and spread of the distribution
as you vary n? Does this seem to agree with
what the formulas for mean and standard deviation tell
you (see bottom of p. 380)?
- In a binomial setting (see p. 376) where we assume
samples of size n, the two most common random
variables are the count of successes and
the proportion of successes. What is the
distinction between these two random variables?
How are they related?